2018/01/18 by Kuntal Dey, Dey, Kuntal, Saroj Kaushik +5
Physics and Astronomy · Social Sciences · #Complex Network Analysis Techniques #Computational and Text Analysis Methods #FOS: Computer and information sciences #FOS: Physical sciences #Opinion Dynamics and Social Influence #Physics and Society (physics.soc-ph) #Social and Information Networks (cs.SI)
paper · pdf · doi:10.48550/arxiv.1801.06161
openalex publication_date 2018/01/18 · openalex created_date 2022/08/09 · openalex updated_date 2026/07/28
Topic lifecycle analysis on Twitter, a branch of study that investigates\nTwitter topics from their birth through lifecycle to death, has gained immense\nmainstream research popularity. In the literature, topics are often treated as\none of (a) hashtags (independent from other hashtags), (b) a burst of keywords\nin a short time span or (c) a latent concept space captured by advanced text\nanalysis methodologies, such as Latent Dirichlet Allocation (LDA). The first\ntwo approaches are not capable of recognizing topics where different users use\ndifferent hashtags to express the same concept (semantically related), while\nthe third approach misses out the user's explicit intent expressed via\nhashtags. In our work, we use a word embedding based approach to cluster\ndifferent hashtags together, and the temporal concurrency of the hashtag\nusages, thus forming topics (a semantically and temporally related group of\nhashtags).We present a novel analysis of topic lifecycles with respect to\ncommunities. We characterize the participation of social communities in the\ntopic clusters, and analyze the lifecycle of topic clusters with respect to\nsuch participation. We derive first-of-its-kind novel insights with respect to\nthe complex evolution of topics over communities and time: temporal morphing of\ntopics over hashtags within communities, how the hashtags die in some\ncommunities but morph into some other hashtags in some other communities (that,\nit is a community-level phenomenon), and how specific communities adopt to\nspecific hashtags. Our work is fundamental in the space of topic lifecycle\nmodeling and understanding in communities: it redefines our understanding of\ntopic lifecycles and shows that the social boundaries of topic lifecycles are\ndeeply ingrained with community behavior.\n